SlideShare uma empresa Scribd logo
1 de 16
BEYOND HASHTAGS: COLLECTING AND
ANALYSING CONVERSATIONS ON TWITTER
Brenda Moon, Nicolas Suzor & Ariadna Matamoros-Fernández
Digital Media Research Centre
Queensland University of Technology
Previous research
• Twitter
– Keywords/hashtags (Rambukkana, 2015; Bruns & Burgess,
2015)
•Network analysis
•Content analysis
– Approaching completeness (Lorentzen & Nolin, 2015)
• We want to catch more of the conversation
Methodology
• Rationale
– Computational analysis (quantitative) + Ethnography /
Visualisation / observation/ description (Qualitative)
• What are these extra tweets telling us?
– Where is the conversation happening? (reply-chains)
– Can we discover new themes? (hashtags)
– Can we discover new actors? (@mentions)
Are they relevant to the issue/controversy/event we are
examining?
Data collection & Uber as a case study
Seed
tweet
in_reply_to
tweet_id
in_reply_to
tweet_id
follow reply chain
back in time using
‘in_reply_to’ field
which contains
the tweet_id of
the replied to
tweet
searching for
tweet_id in
‘in_reply_to’ field
Timeline of Uber Tweets
Case Study:
New Year 2015
New Years Eve 2015 - price surge controversy
Seed Supplement
% of
total
1. Tweets 256,682 53,111 17.1
2. Retweets 84,502 142 0.2
3. Tweeting users 70,584 3,379 4.6
4. Replied to users (by to_user_id) 21,113 6,470 23.5
5a. Replies (by to_user_id) 42,143 46,449 52.4
6a. Mentioned users including RTs 57,151 5,396 8.6
6b. Mentioned users excluding RTs 33,667 6,194 15.5
7a. Mentioned users who sent tweets 9,587 5,099 34.7
7b. Mentioned users who didn't send any tweets 47,564 297 0.6
8. Hashtags (unique hashtags) 21,338 1,773 7.7
New Years Eve 2015 - network metrics - mention
network
Seed Supp % of total contributed
by Supplement
1. Nodes 2,276.00 312 12.06
2. Edges 2,527.00 713 22.01
3. Average weighted degree 2.22 0.28 11.31
4. Max in-degree 295 0 0
5. Max out-degree 27 12 30.77
6. Average path length 2.9 2.36 44.89
Reply chains: conversation network
nodes: 2,345
extra tweets: 70%
seed tweets: 30%
Reply chains: selected chain
nodes: 2,345
extra tweets: 70%
seed tweets: 30%
Original Tweet:
Some of the replies in
the reply chain:
@mentions
@Bencubby
Hashtags
Preliminary Conclusions
• Importance of qualitative observation and
exploration to make sense of complex conversations
on social media
• The method is more useful to identify conversations
and understand context rather than discover new
themes via hashtags (e.g. central issues vs
annotations)
• Visualization helps identify points of interest
Future outlook
• Additional case studies to identify which types of
events reply chain supplementation is useful for.
• Identifying ‘key media objects’
(e.g. highly posted images, videos, or arguments)
and tracing the conversation specifically around
them, rather than our keyword datasets.
•Evolution over time - looking at how these
conversations evolve and change over time
Thank you :)
Brenda Moon @brendam
Nicolas Suzor @nicsuzor
Ariadna Matamoros-Fernández @andairamf
Digital Media Research Centre
Queensland University of Technology
Collecting and Analysing Conversations on Twitter Beyond Hashtags

Mais conteúdo relacionado

Semelhante a Collecting and Analysing Conversations on Twitter Beyond Hashtags

IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...
IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...
IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...IRJET Journal
 
ReMO Budapest Twitter workshop.pdf
ReMO Budapest Twitter workshop.pdfReMO Budapest Twitter workshop.pdf
ReMO Budapest Twitter workshop.pdfGUNERI
 
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...IRJET Journal
 
New Methodologies for Capturing and Working with Publicly Available Twitter Data
New Methodologies for Capturing and Working with Publicly Available Twitter DataNew Methodologies for Capturing and Working with Publicly Available Twitter Data
New Methodologies for Capturing and Working with Publicly Available Twitter DataAxel Bruns
 
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation System
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation SystemLatent Dirichlet Allocation as a Twitter Hashtag Recommendation System
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation SystemShailly Saxena
 
Investigating the Characteristics and Research Impact of Sentiments in Tweets...
Investigating the Characteristics and Research Impact of Sentiments in Tweets...Investigating the Characteristics and Research Impact of Sentiments in Tweets...
Investigating the Characteristics and Research Impact of Sentiments in Tweets...Aravind Sesagiri Raamkumar
 
Beyond MOOCS – A Catalyst for Change
Beyond MOOCS – A Catalyst for ChangeBeyond MOOCS – A Catalyst for Change
Beyond MOOCS – A Catalyst for ChangeFutureLearn FLAN
 
Twitter at an SLP/SLT Conference
Twitter at an SLP/SLT ConferenceTwitter at an SLP/SLT Conference
Twitter at an SLP/SLT ConferenceBronwyn Hemsley
 
Twitter Sentiment Analysis
Twitter Sentiment AnalysisTwitter Sentiment Analysis
Twitter Sentiment Analysisijtsrd
 
Deploying Viva Topics
Deploying Viva TopicsDeploying Viva Topics
Deploying Viva TopicsDrew Madelung
 
Communities of attention' around journal papers: Who is tweeting about scient...
Communities of attention' around journal papers: Who is tweeting about scient...Communities of attention' around journal papers: Who is tweeting about scient...
Communities of attention' around journal papers: Who is tweeting about scient...Stefanie Haustein
 
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...Brenda Moon
 
What makes a tweet relevant for a topic?
What makes a tweet relevant for a topic?What makes a tweet relevant for a topic?
What makes a tweet relevant for a topic?Ke Tao
 
Analyzing the Meaning of the Qualitative Data.pptx
Analyzing the Meaning of the Qualitative Data.pptxAnalyzing the Meaning of the Qualitative Data.pptx
Analyzing the Meaning of the Qualitative Data.pptxBobbyPabores1
 
Learning Analytics: Seeking new insights from educational data
Learning Analytics: Seeking new insights from educational dataLearning Analytics: Seeking new insights from educational data
Learning Analytics: Seeking new insights from educational dataAndrew Deacon
 
NPIN twitter chat NCHCMM 2012
NPIN twitter chat NCHCMM 2012NPIN twitter chat NCHCMM 2012
NPIN twitter chat NCHCMM 2012CDC NPIN
 

Semelhante a Collecting and Analysing Conversations on Twitter Beyond Hashtags (20)

IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...
IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...
IRJET - Socirank Identifying and Ranking Prevalent News Topics using Social M...
 
Bowman.2014 nordicworkshop
Bowman.2014 nordicworkshopBowman.2014 nordicworkshop
Bowman.2014 nordicworkshop
 
ReMO Budapest Twitter workshop.pdf
ReMO Budapest Twitter workshop.pdfReMO Budapest Twitter workshop.pdf
ReMO Budapest Twitter workshop.pdf
 
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
IRJET- A Survey on Trend Analysis on Twitter for Predicting Public Opinion on...
 
Irb Defense
Irb DefenseIrb Defense
Irb Defense
 
New Methodologies for Capturing and Working with Publicly Available Twitter Data
New Methodologies for Capturing and Working with Publicly Available Twitter DataNew Methodologies for Capturing and Working with Publicly Available Twitter Data
New Methodologies for Capturing and Working with Publicly Available Twitter Data
 
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation System
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation SystemLatent Dirichlet Allocation as a Twitter Hashtag Recommendation System
Latent Dirichlet Allocation as a Twitter Hashtag Recommendation System
 
E017433538
E017433538E017433538
E017433538
 
Investigating the Characteristics and Research Impact of Sentiments in Tweets...
Investigating the Characteristics and Research Impact of Sentiments in Tweets...Investigating the Characteristics and Research Impact of Sentiments in Tweets...
Investigating the Characteristics and Research Impact of Sentiments in Tweets...
 
Beyond MOOCS – A Catalyst for Change
Beyond MOOCS – A Catalyst for ChangeBeyond MOOCS – A Catalyst for Change
Beyond MOOCS – A Catalyst for Change
 
Twitter at an SLP/SLT Conference
Twitter at an SLP/SLT ConferenceTwitter at an SLP/SLT Conference
Twitter at an SLP/SLT Conference
 
Twitter Sentiment Analysis
Twitter Sentiment AnalysisTwitter Sentiment Analysis
Twitter Sentiment Analysis
 
Deploying Viva Topics
Deploying Viva TopicsDeploying Viva Topics
Deploying Viva Topics
 
Communities of attention' around journal papers: Who is tweeting about scient...
Communities of attention' around journal papers: Who is tweeting about scient...Communities of attention' around journal papers: Who is tweeting about scient...
Communities of attention' around journal papers: Who is tweeting about scient...
 
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...
A Topic Analysis Approach To Revealing Discussions On The Australian Twitters...
 
sdv.pptx
sdv.pptxsdv.pptx
sdv.pptx
 
What makes a tweet relevant for a topic?
What makes a tweet relevant for a topic?What makes a tweet relevant for a topic?
What makes a tweet relevant for a topic?
 
Analyzing the Meaning of the Qualitative Data.pptx
Analyzing the Meaning of the Qualitative Data.pptxAnalyzing the Meaning of the Qualitative Data.pptx
Analyzing the Meaning of the Qualitative Data.pptx
 
Learning Analytics: Seeking new insights from educational data
Learning Analytics: Seeking new insights from educational dataLearning Analytics: Seeking new insights from educational data
Learning Analytics: Seeking new insights from educational data
 
NPIN twitter chat NCHCMM 2012
NPIN twitter chat NCHCMM 2012NPIN twitter chat NCHCMM 2012
NPIN twitter chat NCHCMM 2012
 

Último

Film show production powerpoint for site
Film show production powerpoint for siteFilm show production powerpoint for site
Film show production powerpoint for siteAshtonCains
 
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call Me
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call MeCall^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call Me
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call MeMs Riya
 
Codes and Conventions of Artists' Websites
Codes and Conventions of Artists' WebsitesCodes and Conventions of Artists' Websites
Codes and Conventions of Artists' WebsitesLukeNash7
 
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECall girl Jaipur
 
This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...samuelcoulson30
 
Ready to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosReady to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosSocioCosmos
 
Film show post-production powerpoint for site
Film show post-production powerpoint for siteFilm show post-production powerpoint for site
Film show post-production powerpoint for siteAshtonCains
 
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service 👖
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service  👖CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service  👖
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service 👖anilsa9823
 
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsCall Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsPooja Nehwal
 
Film show evaluation powerpoint for site
Film show evaluation powerpoint for siteFilm show evaluation powerpoint for site
Film show evaluation powerpoint for siteAshtonCains
 
Film the city investagation powerpoint :)
Film the city investagation powerpoint :)Film the city investagation powerpoint :)
Film the city investagation powerpoint :)AshtonCains
 
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCR
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCRElite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCR
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCRDelhi Call girls
 
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...SocioCosmos
 
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCR
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCRElite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCR
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCRDelhi Call girls
 
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Delhi Call girls
 
Production diary Film the city powerpoint
Production diary Film the city powerpointProduction diary Film the city powerpoint
Production diary Film the city powerpointAshtonCains
 
Website research Powerpoint for Bauer magazine
Website research Powerpoint for Bauer magazineWebsite research Powerpoint for Bauer magazine
Website research Powerpoint for Bauer magazinesamuelcoulson30
 

Último (20)

Bicycle Safety in Focus: Preventing Fatalities and Seeking Justice
Bicycle Safety in Focus: Preventing Fatalities and Seeking JusticeBicycle Safety in Focus: Preventing Fatalities and Seeking Justice
Bicycle Safety in Focus: Preventing Fatalities and Seeking Justice
 
9953056974 Young Call Girls In Kirti Nagar Indian Quality Escort service
9953056974 Young Call Girls In  Kirti Nagar Indian Quality Escort service9953056974 Young Call Girls In  Kirti Nagar Indian Quality Escort service
9953056974 Young Call Girls In Kirti Nagar Indian Quality Escort service
 
Film show production powerpoint for site
Film show production powerpoint for siteFilm show production powerpoint for site
Film show production powerpoint for site
 
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call Me
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call MeCall^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call Me
Call^ Girls Delhi Independent girls Chanakyapuri 9711199012 Call Me
 
Codes and Conventions of Artists' Websites
Codes and Conventions of Artists' WebsitesCodes and Conventions of Artists' Websites
Codes and Conventions of Artists' Websites
 
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFECASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
CASH PAYMENT ON GIRL HAND TO HAND HOUSEWIFE
 
This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...This is a Powerpoint about research into the codes and conventions of a film ...
This is a Powerpoint about research into the codes and conventions of a film ...
 
Vip Call Girls Tilak Nagar ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Tilak Nagar ➡️ Delhi ➡️ 9999965857 No Advance 24HRS LiveVip Call Girls Tilak Nagar ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Tilak Nagar ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
 
Ready to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with SociocosmosReady to get noticed? Partner with Sociocosmos
Ready to get noticed? Partner with Sociocosmos
 
Film show post-production powerpoint for site
Film show post-production powerpoint for siteFilm show post-production powerpoint for site
Film show post-production powerpoint for site
 
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service 👖
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service  👖CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service  👖
CALL ON ➥8923113531 🔝Call Girls Takrohi Lucknow best Female service 👖
 
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy GirlsCall Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
Call Girls In Andheri East Call 9167673311 Book Hot And Sexy Girls
 
Film show evaluation powerpoint for site
Film show evaluation powerpoint for siteFilm show evaluation powerpoint for site
Film show evaluation powerpoint for site
 
Film the city investagation powerpoint :)
Film the city investagation powerpoint :)Film the city investagation powerpoint :)
Film the city investagation powerpoint :)
 
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCR
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCRElite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCR
Elite Class ➥8448380779▻ Call Girls In Nizammuddin Delhi NCR
 
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
 
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCR
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCRElite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCR
Elite Class ➥8448380779▻ Call Girls In New Friends Colony Delhi NCR
 
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
Night 7k Call Girls Atta Market Escorts Call Me: 8448380779
 
Production diary Film the city powerpoint
Production diary Film the city powerpointProduction diary Film the city powerpoint
Production diary Film the city powerpoint
 
Website research Powerpoint for Bauer magazine
Website research Powerpoint for Bauer magazineWebsite research Powerpoint for Bauer magazine
Website research Powerpoint for Bauer magazine
 

Collecting and Analysing Conversations on Twitter Beyond Hashtags

  • 1. BEYOND HASHTAGS: COLLECTING AND ANALYSING CONVERSATIONS ON TWITTER Brenda Moon, Nicolas Suzor & Ariadna Matamoros-Fernández Digital Media Research Centre Queensland University of Technology
  • 2. Previous research • Twitter – Keywords/hashtags (Rambukkana, 2015; Bruns & Burgess, 2015) •Network analysis •Content analysis – Approaching completeness (Lorentzen & Nolin, 2015) • We want to catch more of the conversation
  • 3. Methodology • Rationale – Computational analysis (quantitative) + Ethnography / Visualisation / observation/ description (Qualitative) • What are these extra tweets telling us? – Where is the conversation happening? (reply-chains) – Can we discover new themes? (hashtags) – Can we discover new actors? (@mentions) Are they relevant to the issue/controversy/event we are examining?
  • 4. Data collection & Uber as a case study Seed tweet in_reply_to tweet_id in_reply_to tweet_id follow reply chain back in time using ‘in_reply_to’ field which contains the tweet_id of the replied to tweet searching for tweet_id in ‘in_reply_to’ field
  • 5. Timeline of Uber Tweets Case Study: New Year 2015
  • 6. New Years Eve 2015 - price surge controversy Seed Supplement % of total 1. Tweets 256,682 53,111 17.1 2. Retweets 84,502 142 0.2 3. Tweeting users 70,584 3,379 4.6 4. Replied to users (by to_user_id) 21,113 6,470 23.5 5a. Replies (by to_user_id) 42,143 46,449 52.4 6a. Mentioned users including RTs 57,151 5,396 8.6 6b. Mentioned users excluding RTs 33,667 6,194 15.5 7a. Mentioned users who sent tweets 9,587 5,099 34.7 7b. Mentioned users who didn't send any tweets 47,564 297 0.6 8. Hashtags (unique hashtags) 21,338 1,773 7.7
  • 7. New Years Eve 2015 - network metrics - mention network Seed Supp % of total contributed by Supplement 1. Nodes 2,276.00 312 12.06 2. Edges 2,527.00 713 22.01 3. Average weighted degree 2.22 0.28 11.31 4. Max in-degree 295 0 0 5. Max out-degree 27 12 30.77 6. Average path length 2.9 2.36 44.89
  • 8. Reply chains: conversation network nodes: 2,345 extra tweets: 70% seed tweets: 30%
  • 9. Reply chains: selected chain nodes: 2,345 extra tweets: 70% seed tweets: 30%
  • 10. Original Tweet: Some of the replies in the reply chain:
  • 13. Preliminary Conclusions • Importance of qualitative observation and exploration to make sense of complex conversations on social media • The method is more useful to identify conversations and understand context rather than discover new themes via hashtags (e.g. central issues vs annotations) • Visualization helps identify points of interest
  • 14. Future outlook • Additional case studies to identify which types of events reply chain supplementation is useful for. • Identifying ‘key media objects’ (e.g. highly posted images, videos, or arguments) and tracing the conversation specifically around them, rather than our keyword datasets. •Evolution over time - looking at how these conversations evolve and change over time
  • 15. Thank you :) Brenda Moon @brendam Nicolas Suzor @nicsuzor Ariadna Matamoros-Fernández @andairamf Digital Media Research Centre Queensland University of Technology